Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    independence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replenish
    -0.08
    dose
    -0.08
    798
    -0.08
     ingestion
    -0.07
    数字
    -0.07
     PAS
    -0.07
     sorted
    -0.07
     dose
    -0.07
     Intersection
    -0.07
     accompany
    -0.07
    POSITIVE LOGITS
     autonomy
    0.17
     autonomía
    0.15
     استقلال
    0.15
    自主
    0.14
     onafhankelijk
    0.14
     самостоятель
    0.14
     автоном
    0.14
     независ
    0.14
     independencia
    0.14
     independence
    0.13
    Act Density 0.052%

    No Known Activations